Abstract : Recent years' most efficient approaches for language understanding are statistical. These approaches benefit from a segmental semantic annotation of corpora. To reduce the production cost of such corpora, this paper proposes a method that is able to match first identified concepts with word sequences in an unsuper-vised way. This method based on automatic alignment is used by an understanding system based on conditional random fields and is evaluated on a spoken dialogue task using either manual or automatic transcripts.
Stéphane Huet, Fabrice Lefèvre. Unsupervised Alignment for Segmental-based Language Understanding. EMNLP Workshop on Unsupervised Learning in NLP (UNSUP), Aug 2011, Edinburgh, United Kingdom. pp.97-104. ⟨hal-01317563⟩